Evaluation of Fault-tolerant Distributed Web Systems

Hong, Yoo S.; No, Jaechun; Han, In Kyu

doi:10.1109/words.2005.35

Cited by 4 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resultant efficient service delivery credited the performability of the architecture solution with an insignificant variation in guaranteeing the system's behavior -performance. The result findings were also synonymous with literary works in performance computing (Hong et al, 2005;Peng & Huang, 2014;Pandey et al, 2019). Saha (2009) discoursed that "software-based fault tolerance is the use of technologies to enable the continued delivery of services at an acceptable level of performance after a design fault becomes active".…”

Section: Figure 10supporting

confidence: 66%

“…The outcomes of the simulated experiments and evaluation were in harmony with literary works in service-oriented system communities (Hong et al, 2005;Calisti et al, 2010;Alvi et al, 2019;Pandey et al, 2019). Convincingly, the architecture solution's performance was contrary to the latency and replica-related overheads observed in some other studies (Aghdaie & Tamir, 2002;Li et al, 2005;Zhao, 2007;Rickard & Oskar, 2017;Li et al, 2018;Dahling et al, 2021).…”

Section: Discussionsupporting

confidence: 53%

“…In view of the replication issues related to the developments of faulttolerant web systems, Hong et al (2005) proposed a replication (active and passive) approach for fault tolerance in distributed web systems. Performance was evaluated via request generator and LoadCube using the response time metric in the absence and presence of a fault.…”

Section: Related Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Guaranteeing Performance in a Fault Tolerant Architecture Solution using Software Agent’s Coordination

Oliha

2022

JICT

View full text Add to dashboard Cite

Performance is a critical attribute in evaluating the quality and dependability of service-oriented systems dependent on fault-tolerantarchitectures. Fault-tolerant architectures have been implemented with redundant techniques to ensure fault-tolerant services. However, replica-related overhead burdens fault-tolerant techniques with associated performance degradation in service delivery, and this consequentially discourages service consumers with discredits for service providers. In this paper, a fault-tolerant approach thatadopts replication and diversity was employed on agent-oriented coordination toward guaranteeing the performance of the proposedfault-tolerant architecture solution under a large-scale service request load. In addition, the resultant architecture solution was simulated with Apache JMeter for performance evaluation considering the performability in the absence and presence of a fault load. The simulation experiments and results revealed the architecture’s efficiency in fault tolerance via the timely coordination of logicaland replica-related activities by software agents. Noteworthily, the continued service availability and performance were guaranteed for the architecture solution with a significant rate of regularity in the absence and presence of a replica-related fault. Therefore, this study’s performance evaluation methods and results could serve as a veritable milestone for building fault-tolerant service systems with appreciable performability and contribute to the service-oriented fields where performance is inevitable.

show abstract

Section: Figure 10supporting

confidence: 66%

Section: Discussionsupporting

confidence: 53%

Section: Related Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Guaranteeing Performance in a Fault Tolerant Architecture Solution using Software Agent’s Coordination

Oliha

2022

JICT

View full text Add to dashboard Cite

show abstract

“…Clients send requests to the LVS. The LVS-based load balancer distributes requests to one of the servers [7,19]. The load balancer can be mirrored to provide high availability.…”

Section: Adaptive Clustering With Lblcr Schedulingmentioning

confidence: 99%

“…When the demand recedes, the particular server set will contract, releasing the newly recruited server to the cluster. Locality-based least connection with replication (LBLCR) scheduling that comes with Linux is designed to adapt to different traffic patterns in a cluster [19]. Linux Virtual Server (LVS)-based load balancer [9,26] distributes client requests to back-end servers based on the number of connections between the LVS load balancer and the back-end servers.…”

Section: Introductionmentioning

confidence: 99%

Autonomous learning of load and traffic patterns to improve cluster utilization

2011

View full text Add to dashboard Cite

Adaptive clustering aims at improving cluster utilization for varying load and traffic patterns. Localitybased least-connection with replication (LBLCR) scheduling that comes with Linux is designed to help improve cluster utilization through adaptive clustering. A key issue with LBLCR, however, is that cluster performance depends much on a single threshold value that is used to determine adaptation. Once set, the threshold remains fixed, regardless of the load and traffic patterns. If a cluster of PCs is to adapt to different traffic patterns for high utilization, a good threshold has to be selected and used dynamically. We present in this paper an adaptive clustering framework that autonomously learns and adapts to different load and traffic patterns at runtime with no administrator intervention. The cluster is configured once and for all. As the patterns change, the cluster automatically expands/contracts to meet the changing demands. At the same time, the patterns are proactively learned so that when similar patterns emerge in the future, the cluster knows what to do to improve utilization. We have implemented this autonomous learning method and compared it with LBLCR using published Web traces. Experimental results indicate that our autonomous learning method produces high performance scalability and adaptability for different patterns. On the other hand LBLCR-based clustering suffers from performance scalability and adaptability for different traffic patterns since it is not designed to obtain good threshold values and use them at runtime.

show abstract

DNS-Based Load Balancing in Distributed Web-server Systems

Hong

Kim

The Fourth IEEE Workshop on Software Technologies for Future Embedded and Ubiquitous Systems, and the Second International Work

View full text Add to dashboard Cite

Evaluation of Fault-tolerant Distributed Web Systems

Cited by 4 publications

References 8 publications

Guaranteeing Performance in a Fault Tolerant Architecture Solution using Software Agent’s Coordination

Guaranteeing Performance in a Fault Tolerant Architecture Solution using Software Agent’s Coordination

Autonomous learning of load and traffic patterns to improve cluster utilization

DNS-Based Load Balancing in Distributed Web-server Systems

Contact Info

Product

Resources

About